INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     cant
    -0.09
     Chateau
    -0.08
     cib
    -0.08
     sonic
    -0.07
     insinu
    -0.07
    infeld
    -0.07
    ению
    -0.07
    ulog
    -0.07
     sofr
    -0.07
    cant
    -0.07
    POSITIVE LOGITS
    Fully
    0.09
     полноцен
    0.09
     Students
    0.08
     Full
    0.08
    FULL
    0.08
     Fully
    0.08
     universitaire
    0.08
    ূর্ণ
    0.08
    Paid
    0.08
    	full
    0.08
    Act Density 0.022%

    No Known Activations